Code and documentation to train Stanford's Alpaca models, and generate the data.
-
Updated
Jul 17, 2024 - Python
Code and documentation to train Stanford's Alpaca models, and generate the data.
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
An Open-sourced Knowledgable Large Language Model Framework.
A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.
PhoGPT: Generative Pre-training for Vietnamese (2023)
[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI
[NeurIPS'23] "MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing".
EVE Series: Encoder-Free Vision-Language Models from BAAI
[ICLR 2024] Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models
[EMNLP 2023] Lion: Adversarial Distillation of Proprietary Large Language Models
Finetune LLaMA-7B with Chinese instruction datasets
EditWorld: Simulating World Dynamics for Instruction-Following Image Editing
[CVPR 2025] UniGoal: Towards Universal Zero-shot Goal-oriented Navigation
[ACL 2024] FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models
Official repository for KoMT-Bench built by LG AI Research
Instruction Following Agents with Multimodal Transforemrs
🌱 梦想家(DreamerGPT):中文大语言模型指令精调
An benchmark for evaluating the capabilities of large vision-language models (LVLMs)
Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]
This repo hosts the Python SDK and related examples for AIMon, which is a proprietary, state-of-the-art system for detecting LLM quality issues such as Hallucinations. It can be used during offline evals, continuous monitoring or inline detection. We offer various model quality metrics that are fast, reliable and cost-effective.
Add a description, image, and links to the instruction-following topic page so that developers can more easily learn about it.
To associate your repository with the instruction-following topic, visit your repo's landing page and select "manage topics."